© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135710
    Prev
    Next
    INDEX
    Explanations

    databases and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     أد
    0.45
    ن
    0.43
    йна
    0.43
    ኩል
    0.43
    ahiye
    0.42
    น
    0.42
    teren
    0.42
     indentation
    0.42
    峮
    0.41
    ague
    0.41
    POSITIVE LOGITS
     Whenever
    0.51
    𝗽
    0.47
     Raff
    0.45
     Suffering
    0.43
    Swiss
    0.43
    しば
    0.43
    raff
    0.42
    anniksi
    0.42
     Sometimes
    0.42
     socially
    0.41
    Activations Density 0.001%

    No Known Activations